Re: [patch V3 19/22] timer: Forward wheel clock whenever possible

From	Thomas Gleixner <tglx@linutronix.de>
Newsgroups	linux.kernel
Subject	Re: [patch V3 19/22] timer: Forward wheel clock whenever possible
Date	2016-06-25 11:00 +0200
Message-ID	<rNRBv-3iY-9@gated-at.bofh.it> (permalink)
References	<rNAqZ-NX-3@gated-at.bofh.it> <rNAr0-NX-37@gated-at.bofh.it> <rNGd3-4B8-1@gated-at.bofh.it>
Organization	linux.* mail to news gateway

Show all headers | View raw

On Fri, 24 Jun 2016, Richard Cochran wrote:

> On Fri, Jun 24, 2016 at 02:32:19PM -0000, Thomas Gleixner wrote:
> > @@ -809,6 +815,12 @@ static void tick_nohz_restart_sched_tick
> >  	tick_do_update_jiffies64(now);
> >  	cpu_load_update_nohz_stop();
> >  
> > +	/*
> > +	 * Clear the timer idle flag, so we avoid IPIs on remote queueing and
> > +	 * the clock forward checks in the enqueue path.
> > +	 */
> > +	timer_clear_idle();
> 
> Since function calls timer_clear_idle() already ...
>
> >  	calc_load_exit_idle();
> >  	touch_softlockup_watchdog_sched();
> >  	/*
> > @@ -1025,6 +1037,7 @@ void tick_nohz_idle_exit(void)
> >  		tick_nohz_stop_idle(ts, now);
> >  
> >  	if (ts->tick_stopped) {
> > +		timer_clear_idle();
> >  		tick_nohz_restart_sched_tick(ts, now);
> >  		tick_nohz_account_idle_ticks(ts);
> >  	}
> 
> ... there is no need to call timer_clear_idle() here.

Indeed.

Back to linux.kernel | Previous | Next — Previous in thread | Find similar | Unroll thread

Thread

[patch V3 19/22] timer: Forward wheel clock whenever possible Thomas Gleixner <tglx@linutronix.de> - 2016-06-24 16:40 +0200
  Re: [patch V3 19/22] timer: Forward wheel clock whenever possible Richard Cochran <richardcochran@gmail.com> - 2016-06-24 22:50 +0200
    Re: [patch V3 19/22] timer: Forward wheel clock whenever possible Thomas Gleixner <tglx@linutronix.de> - 2016-06-25 11:00 +0200

csiph-web